mcpField
A
Agent Toolbox

Agent Toolbox

Local
agent-toolbox.aiAI & Agents0Updated 15w ago
RepositoryVisit website

About Agent Toolbox

Agent Toolbox is a local MCP server offering code, output, security, privacy, and finance checks for AI agents. It runs over stdio without an API key or environment variables.

Key features

  1. 01Validate imports and verify outputs
  2. 02Distill context and count tokens
  3. 03Scan for secrets, injection, vulnerabilities, and PII
  4. 04Check finance units, prices, and symbols
  5. 05Assess token, slippage, order, and position risk

Use cases

  1. 01Validate code imports before an action
  2. 02Check generated output quality
  3. 03Scan content for sensitive data or injection
  4. 04Review financial parameters and trade risks

MCP support

Exposes 15 tools to MCP-compatible clients over stdio, including code and output checks, security and privacy scans, and finance checks. It runs locally and requires no API key or environment variables.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "solhammer-agent-toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "agentoolbox-mcp"
      ]
    }
  }
}
Run commandnpx -y agentoolbox-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmagentoolbox-mcp0.1.4

Tools

26

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
codestringYesThe AI-generated code to validate.
languageenumYesThe programming language of the code snippet.python | javascript | typescript | rust | go
timeoutMsnumberNoRegistry request timeout in ms (default: 5000).

Details

From the project README

agentoolbox-mcp

MCP server for agent-toolbox.ai — the quality layer for AI agents. Exposes code- and output-quality tools to Claude, Cursor, Warp, Cline, and any MCP-compatible client over stdio.

Tools (15)

Core: validate_imports, verify_output, distill_context Security & privacy: scan_secrets, scan_injection, count_tokens, scan_vulnerabilities, scan_pii Finance: finance_units, finance_price, finance_symbol, finance_token_risk, finance_slippage, finance_order_risk, finance_position_check Runs locally over stdio, in-process — no API key or env vars (free public data sources only).

Install

No clone or build needed:

{
  "mcpServers": {
    "agent-toolbox": { "command": "npx", "args": ["-y", "agentoolbox-mcp"] }
  }
}

Or build from source:

git clone https://github.com/solhammer/agentoolbox
cd agentoolbox
pnpm install
pnpm --filter "agentoolbox-mcp..." build   # builds the server + its workspace deps

This produces packages/mcp/dist/index.js (use "command": "node" with its absolute path).

Configure your MCP client

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Cursor: ~/.cursor/mcp.json
  • Warp: Settings → Agents → MCP servers → Add
{
  "mcpServers": {
    "agent-toolbox": {
      "command": "node",
      "args": ["/absolute/path/to/agentoolbox/packages/mcp/dist/index.js"]
    }
  }
}

Replace /absolute/path/to/agentoolbox with the path where you cloned the repo.

More

The full REST API lives at api.agent-toolbox.ai; all 15 tools are exposed over MCP. License: MIT.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.